Hey guys, does the get_spans_dataframe api call store the llm cost of that span? If not, is there a way to extract that? or will that need to be calculated using the tokens and the model being used ourselves?
馃挕聽Hint: Mention RunLLM in the thread for followups.
Hi Suhrullekha C., unfortunately there isn't an explicit field for the cost of the span when you do get_spans_dataframe. The best work around would be to compute the cost based on the token_count fields.
Suhrullekha C. Please feel free to file us an enhancement request.
